© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56611
    Prev
    Next
    INDEX
    Explanations

    rugged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    従って
    0.66
    therefore
    0.66
     Со
    0.64
     Ла
    0.62
    ငံ
    0.61
    ሆነ
    0.61
    وں
    0.60
    粌
    0.59
    പ്പാ
    0.59
    MktCap
    0.58
    POSITIVE LOGITS
    y
    0.74
     of
    0.71
     at
    0.67
     on
    0.61
    ا
    0.59
    i
    0.58
     in
    0.56
    م
    0.55
     t
    0.55
     that
    0.55
    Activations Density 0.001%

    No Known Activations